Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1571 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0888. Min Act: -0.1700

Data Index: 7026305 (Open Web Text)

Max Activating Token Index: 719

Text #1

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0848. Min Act: -0.1700

Data Index: 660324 (Open Web Text)

Max Activating Token Index: 997

Text #2

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0749. Min Act: -0.1700

Data Index: 5920025 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0709. Min Act: -0.1700

Data Index: 197021 (Open Web Text)

Max Activating Token Index: 851

Text #4

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0621. Min Act: -0.1700

Data Index: 4790607 (Open Web Text)

Max Activating Token Index: 997

Text #5

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0761. Min Act: -0.1700

Data Index: 4761976 (Open Web Text)

Max Activating Token Index: 817

Text #6

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0546. Min Act: -0.1700

Data Index: 3315846 (Open Web Text)

Max Activating Token Index: 459

Text #7

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0537. Min Act: -0.1700

Data Index: 8053179 (Open Web Text)

Max Activating Token Index: 530

Text #8

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0542. Min Act: -0.1700

Data Index: 3557432 (Open Web Text)

Max Activating Token Index: 934

Text #9

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0376. Min Act: -0.1700

Data Index: 2765919 (Open Web Text)

Max Activating Token Index: 971

Text #10

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0376. Min Act: -0.1700

Data Index: 2765918 (Open Web Text)

Max Activating Token Index: 537

Text #11

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0397. Min Act: -0.1700

Data Index: 6968031 (Open Web Text)

Max Activating Token Index: 61

Text #12

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0361. Min Act: -0.1700

Data Index: 1996144 (Open Web Text)

Max Activating Token Index: 268

Text #13

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0186. Min Act: -0.1700

Data Index: 5591001 (Open Web Text)

Max Activating Token Index: 131

Text #14

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0173. Min Act: -0.1700

Data Index: 4689093 (Open Web Text)

Max Activating Token Index: 556

Text #15

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0322. Min Act: -0.1700

Data Index: 3512227 (Open Web Text)

Max Activating Token Index: 261

Text #16

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0315. Min Act: -0.1700

Data Index: 4821419 (Open Web Text)

Max Activating Token Index: 524

Text #17

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0073. Min Act: -0.1700

Data Index: 4489558 (Open Web Text)

Max Activating Token Index: 765

Text #18

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0082. Min Act: -0.1700

Data Index: 2032440 (Open Web Text)

Max Activating Token Index: 813

Text #19

Max Range: 3.0888. Min Range: -3.0888

Max Act: 3.0123. Min Act: -0.1700

Data Index: 5789862 (Open Web Text)

Max Activating Token Index: 301